Skip to content

Predicted Latency based routing - support disagg scenarios #1923

@kaushikmitr

Description

@kaushikmitr

Update the Predicted Latency based scorer if prefill/decode steps are disaggregated

Metadata

Metadata

Assignees

Labels

triage/acceptedIndicates an issue or PR is ready to be actively worked on.

Type

No type

Projects

No projects

Relationships

None yet

Development

No branches or pull requests

Issue actions